IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation
作者: Varun Gumma, Navonil Majumder, Soumitra Sinhahajari, Soujanya Poria
分类: cs.AI
发布日期: 2026-07-24
备注: Under Review
🔗 代码/项目: GITHUB
💡 一句话要点
提出IDEAgent以解决研究创意生成中的质量与多样性问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 创意生成 质量-多样性搜索 多代理系统 科学发现 大型语言模型
📋 核心要点
- 现有方法在生成创意时仅关注质量或多样性,导致创意相似或缺乏深度,影响科学发现的效率。
- IDEAgent通过多代理框架同时优化创意的质量与多样性,采用多目标反馈和轻量级记忆机制进行创意演变管理。
- 在32个计算机科学主题的评估中,IDEAgent的Yield指标表现优于最佳基线3.89倍,并在更多主题上实现有效创意生成。
📝 摘要(中文)
近年来,大型语言模型(LLMs)显著自动化了科学发现的过程。然而,现有系统在生成和优化创意时存在一个核心限制:它们独立处理质量或多样性,导致生成的创意相互接近或产生大量琐碎、不合理或不清晰的概念。本文提出IDEAgent,一个多代理框架,通过血统管理创意的演变,联合驱动质量和多样性。我们开发了Yield指标,系统评估质量与多样性的结合。实验结果显示,IDEAgent在32个主题上超越最佳基线3.89倍,并在8倍更多主题上实现非零Yield,验证了修复和精炼对逻辑严谨性和清晰度的重要性。
🔬 方法详解
问题定义:本文旨在解决现有创意生成方法在质量与多样性之间的独立优化问题,导致生成的创意缺乏深度和多样性。
核心思路:IDEAgent将研究创意生成视为质量与多样性的结合,通过多代理框架管理创意演变,确保生成的创意既高质量又多样化。
技术框架:IDEAgent的整体架构包括多个代理,利用多目标反馈进行质量优化,同时通过轻量级的顺序记忆和对比机制实现多样性。
关键创新:最重要的创新在于引入了Yield指标,系统性地评估质量与多样性的结合,推动了创意生成的逻辑严谨性和清晰度。
关键设计:在设计中,采用了多目标反馈机制进行创意修复和精炼,确保生成的创意不仅符合质量标准,还具备足够的多样性。
🖼️ 关键图片
📊 实验亮点
在32个计算机科学主题的评估中,IDEAgent的Yield指标表现超越最佳基线3.89倍,并在8倍更多主题上实现非零Yield,显示出其在创意生成中的显著优势。实验结果进一步验证了修复和精炼对提升创意质量的重要性。
🎯 应用场景
IDEAgent的研究成果可广泛应用于科学研究、技术创新和创意产业等领域,帮助研究人员和企业在创意生成过程中实现更高的效率和质量。未来,IDEAgent可能推动更多基于质量-多样性搜索的创意生成工具的开发,促进科学发现和技术进步。
📄 摘要(原文)
Large Language Models (LLMs) have significantly automated the process of scientific discovery over the past few years. However, existing systems share one core limitation: they generate and optimize ideas independently for either Quality or Diversity. This often leads to the generation of ideas in close proximity to one another or to a large set of trivial, unsound, or unclear concepts. In this work, we instead argue that research ideation should be treated as a conjunction of both objectives and framed as a Quality-Diversity (QD) search. In line with this perspective, we introduce IDEAgent, a multi-agent framework that manages the evolution of ideas through lineages. We jointly drive Quality using multi-objective feedback for dedicated repair and refinement, while Diversity is achieved through lightweight sequential memory and explicit comparison against completed ideas, their historical ancestors, and rejected proposals. To systematically evaluate this QD conjunction, we develop Yield, a joint metric that computes the largest set of mutually diverse ideas that satisfy a predetermined quality threshold. Finally, through evaluations across 32 topics spanning 8 domains of Computer Science, we show that IDEAgent outperforms the best baseline by 3.89x on Yield, while achieving non-zero Yield on 8x more topics. We further corroborate these findings through an analysis of quality improvements, showing that repair and refinement are crucial for building logical rigor and clarity while preserving non-obviousness. To encourage future research on QD-search-based ideation, we open-source IDEAgent at https://github.com/declare-lab/IDEAgent.